An Effective Image Fusion Technique based on Multiresolution Singular Value Decomposition

Abstract

The main objective of image fusion is to combine the multiple images of same scene into a single image having more information and better visual appearance, without introducing any artifacts. In this paper, a new multifocus image fusion scheme based on sharpness and Multiresolution Singular Value Decomposition (MSVD) is proposed to get an image with better visual quality. The proposed scheme is conducted into two parts. In first part, each of the source images is decomposed using Discrete Wavelet Transform (DWT). In second part, obtained low and high frequency DWT coefficients are fused using MSVD and gradient based sharpness approach. To reconstruct a fused image, inverse DWT is performed. The resultant fused image is enhanced and completed as compared to any of the source image. The experimental results obtained by proposed scheme are compared with the existing schemes. The experimental results and comparison demonstrate the effectiveness of proposed scheme.